ClawHub

Buymeacoffee Autobot

Security checks across malware telemetry and agentic risk

Overview

This skill is a review-risk because it asks an agent to automate logged-in creator accounts, including posting, messaging supporters, and reading earnings, without clear approval or safety limits.

Install only if you are comfortable giving an agent stored credentials for a monetized creator account. Require manual confirmation before any post, message, promotion, or earnings scrape, and prefer a dedicated low-privilege account or revocable credentials where possible.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The skill is presented as a general automation capability for posting, thanking supporters, promoting pages, and scraping earnings, but it does not define clear trigger conditions, scope boundaries, or approval requirements. In an agent setting, broad activation language can cause the skill to run in unintended contexts and perform account-affecting actions without sufficiently explicit user intent.

Missing User Warnings

High
Confidence
96% confidence
Finding
The skill explicitly describes browser automation, posting, supporter messaging, scraping earnings, and use of stored login credentials, yet provides no warning about account compromise risk, privacy implications, platform policy violations, or unintended external actions. This is dangerous because it normalizes high-risk automation over a monetization account and could lead to unauthorized posts, exposure of sensitive supporter data, credential misuse, or account suspension.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal